Adaptive digital tissue deconvolution.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38940181", "kind": "science-record", "revision": 2, "content_hash": "sha256:475782840650a43c39b364a7c985e2f5330118154f6ce00d07ebbc3ff17c89b0", "created_at": "2026-11-01T20:29:01Z", "updated_at": "2026-11-01T21:33:22Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Adaptive digital tissue deconvolution.", "doi": "10.1093/bioinformatics/btae263", "pmid": "38940181", "authors": ["Franziska Görtler", "Malte Mensching-Buhr", "Ørjan Skaar", "Stefan Schrod", "Thomas Sterr", "Andreas Schäfer", "Tim Beißbarth", "Anagha Joshi", "Helena U Zacharias", "Sushma Nagaraja Grellscheid", "Michael Altenbuchinger"], "journal": "Bioinformatics (Oxford, England)", "year": 2024, "abstract": "MOTIVATION: The inference of cellular compositions from bulk and spatial transcriptomics data increasingly complements data analyses. Multiple computational approaches were suggested and recently, machine learning techniques were developed to systematically improve estimates. Such approaches allow to infer additional, less abundant cell types. However, they rely on training data which do not capture the full biological diversity encountered in transcriptomics analyses; data can contain cellular contributions not seen in the training data and as such, analyses can be biased or blurred. Thus, computational approaches have to deal with unknown, hidden contributions. Moreover, most methods are based on cellular archetypes which serve as a reference; e.g. a generic T-cell profile is used to infer the proportion of T-cells. It is well known that cells adapt their molecular phenotype to the environment and that pre-specified cell archetypes can distort the inference of cellular compositions.\nRESULTS: We propose Adaptive Digital Tissue Deconvolution (ADTD) to estimate cellular proportions of pre-selected cell types together with possibly unknown and hidden background contributions. Moreover, ADTD adapts prototypic reference profiles to the molecular environment of the cells, which further resolves cell-type specific gene regulation from bulk transcriptomics data. We verify this in simulation studies and demonstrate that ADTD improves existing approaches in estimating cellular compositions. In an application to bulk transcriptomics data from breast cancer patients, we demonstrate that ADTD provides insights into cell-type specific molecular differences between breast cancer subtypes.\nAVAILABILITY AND IMPLEMENTATION: A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362).", "claims": [{"id": "claim-method", "statement": "Adaptive Digital Tissue Deconvolution (ADTD) builds on loss-function learning for DTD introduced previously by Görtler et al. (2020) and extends it by both accounting for unknown background contributions and adaptive reference profiles.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38940181", "locator": "sections[2] \"2 Methods\" paragraph 2", "quote": "Adaptive Digital Tissue Deconvolution (ADTD) builds on loss-function learning for DTD introduced previously by Görtler et al. (2020) and extends it by both accounting for unknown background contributions and adaptive reference profiles."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38940181", "locator": "sections[34] \"Data availability\" paragraph 2", "quote": "All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We observe that ADTD translates best to these first validation data with minimal performance losses compared to the training data (mean Pearson’s correlation over all cell types; r¯=0.864 ± 0.004).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38940181", "locator": "sections[19] \"3.1.2 Validation performance\" paragraph 3", "quote": "We observe that ADTD translates best to these first validation data with minimal performance losses compared to the training data (mean Pearson’s correlation over all cell types; r¯=0.864 ± 0.004)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We observe that ADTD translates best to these first validation data with minimal performance losses compared to the training data (mean Pearson’s correlation over all cell types; r¯=0.864 ± 0.004).", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:38940181"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE164898"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE164898"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38940181", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btae263", "sha256": "sha256:d12f94f5e50aa2c339c0c79c87bdbca6c4dccfc237eb2b5f9ee992c27bfe717a", "bytes": 47465, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btae263", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11256946", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE164898", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164898", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE164898", "version": null, "note": "All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5022599", "GSM5022600", "GSM5022601", "GSM5022602", "GSM5022603", "GSM5022604", "GSM5022605", "GSM5022606"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Single cell atlas of the healthy breast", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE176078", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE176078", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE176078", "version": null, "note": "All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5354513", "GSM5354514", "GSM5354515", "GSM5354516", "GSM5354517", "GSM5354518", "GSM5354519", "GSM5354520", "GSM5354521", "GSM5354522", "GSM5354523", "GSM5354524", "GSM5354525", "GSM5354526", "GSM5354527", "GSM5354528", "GSM5354529", "GSM5354530", "GSM5354531", "GSM5354532", "GSM5354533", "GSM5354534", "GSM5354535", "GSM5354536", "GSM5354537", "GSM5354538"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "A single-cell and spatially resolved atlas of human breast cancers", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE164898 not downloaded", "asset:data:geo:GSE164898 licence not read", "asset:data:geo:GSE176078 not downloaded", "asset:data:geo:GSE176078 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Adaptive Digital Tissue Deconvolution (ADTD)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Adaptive Digital Tissue Deconvolution (ADTD) builds on loss-function learning for DTD introduced previously by Görtler et al. (2020) and extends it by both accounting for unknown background contributions and adaptive reference profiles."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Adaptive Digital Tissue Deconvolution (ADTD)), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE164898", "GSE176078"], "resolved_accessions": ["GSE164898", "GSE176078"], "statements": ["All data used in this article are publicly available. The Gene Expression Omnibus accession numbers to obtain the raw datasets are: scRNA-Seq of healthy breast tissues are available from Bhat-Nakshatri et al. (2021) (GSE164898) and breast cancer scRNA-Seq from Wu et al. (2021) (GSE176078). The BRCA bulk transcriptomics data were generated by the TCGA Research Network (The Cancer Genome Atlas, TCGA). A python implementation of ADTD and a tutorial are available at Gitlab and zenodo (doi:10.5281/zenodo.7548362)."], "basis": "The paper names GSE164898, GSE176078 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:38940181", "data:geo:GSE164898"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE164898"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:22:38Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13478, "completion_tokens": 1874, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:38940181", "type": "paper", "label": "pmid:38940181"}, {"id": "source:pmid:38940181", "type": "manuscript", "label": "PMID 38940181 full text"}, {"id": "data:geo:GSE164898", "type": "dataset", "label": "GEO GSE164898"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38940181", "type": "paper", "label": "pmid:38940181"}, {"id": "source:pmid:38940181", "type": "manuscript", "label": "PMID 38940181 full text"}, {"id": "data:geo:GSE164898", "type": "dataset", "label": "GEO GSE164898"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38940181", "type": "extraction", "used": ["source:pmid:38940181"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE164898", "type": "accession_resolution", "used": ["data:geo:GSE164898"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:38940181", "parent_hash": "sha256:6479f2ba227c988777de8651d1396357b04fe29be87eb826ad453dcdd15653ad", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE164898 licence not read", "asset:data:geo:GSE164898 not downloaded", "asset:data:geo:GSE176078 licence not read", "asset:data:geo:GSE176078 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "methylation_array", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["pared it to two different implementations of EPIC (Racle et al. 2017), one using our own refer", "e matrix X generated from the training data (EPIC 1) and the originally suggested version usin", "d the originally suggested version using the EPIC built-in reference matrix (EPIC 2). EPIC 2 r", "on using the EPIC built-in reference matrix (EPIC 2). EPIC 2 returns only estimates for B-cell"], "order_basis": "paper_text_order:2334", "id": "assay:1"}]}